• Smart Media Journal
• /
• v.13 no.7
• /
• pp.36-44
• /
• 2024

Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium 19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.3
• /
• pp.215-222
• /
• 2019

A frequency hopping(FH) signal can change its carrier frequency during transmission and has spread-spectrum characteristics in these frequency bands. Therefore, FH signals are widely used in applications that require low-probability-of-intercept(LPI) and anti-jamming (AJ) abilities in wireless communication environments. In this study, the authors propose a method for generating hopping information (HI), which includes start time, dwell time, and hopping frequency for unknown FH signals. The proposed blind HI generation method produces signal detection information based on the spectrum data and then extracts HI using operational procedures for estimating the target FH signal's status, such as appearance, maintenance, and termination. Further, simulation results demonstrate that the proposed method provides accurate HI without detection omissions for various FH signals.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.1
• /
• pp.145-155
• /
• 2010

This paper presents a new approach to obstacle avoidance for mobile robot in unknown or partially unknown environments. The method combines two navigation subsystems: low level and high level. The low level subsystem takes part in the control of linear, angular velocities using a multivariable PI controller, and the nonlinear position control. The high level subsystem uses ultrasonic and IR sensors to detect the unknown obstacle include static and dynamic obstacle. This approach provides both obstacle avoidance and target-following behaviors and uses only the local information for decision making for the next action. Also, we propose a new algorithm for the identification and solution of the local minima situation during the robot's traversal using the set of fuzzy rules. The system has been successfully demonstrated by simulations and experiments.

• The Journal of Korea Robotics Society
• /
• v.10 no.4
• /
• pp.223-229
• /
• 2015

This paper proposes a novel method for detection of hand raising poses from images acquired from a single camera attached to a mobile robot that navigates unknown dynamic environments. Due to unconstrained illumination, a high level of variance in human appearances and unpredictable backgrounds, detecting hand raising gestures from an image acquired from a camera attached to a mobile robot is very challenging. The proposed method first detects faces to determine the region of interest (ROI), and in this ROI, we detect hands by using a HOG-based hand detector. By using the color distribution of the face region, we evaluate each candidate in the detected hand region. To deal with cases of failure in face detection, we also use a HOG-based hand raising pose detector. Unlike other hand raising pose detector systems, we evaluate our algorithm with images acquired from the camera and images obtained from the Internet that contain unknown backgrounds and unconstrained illumination. The level of variance in hand raising poses in these images is very high. Our experiment results show that the proposed method robustly detects hand raising poses in complex backgrounds and unknown lighting conditions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.500-503
• /
• 2003

The navigation problem of robot is one of the main themes to deal with conficts or interferences between obstacles and the robot itself In this case, while the robot avoids obstacles on the space, the passage route should be determined efficiently. In order to solve problems above, we have come up with the distance field space medel (DFM) and then, under known environment, we have presented the distance field A algorithm for passage route path search. In this research, the method of performing the 3-dimensional passage route path search of robot under unknown environment is proposed. It is shown that the authors can build the distance search model the does not need space division by taking into account of sensor information to a distance field space model, and constructing this information as virtual obstacle information.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.182-189
• /
• 1999

In this paper, we present an ultrasonic sensor based path planning method using fuzzy logic for obstacle avoidance of an intelligent vehicle in unknown environments. Generally, Robot navigation in unknown terrains is a very complex task difficult to control because of the great amount of imprecise and ambiguous sensor information that has to be considered. In this case, fuzzy logic can satisfactorily deal with such information in quite efficient manner. In this study, we propose two fuzzy logic controller which is composed of steering controller and velocity controller respectively. Our object is to develop a fuzzy controller that can enable a mobile robot to navigate from a start point to a goal point without collisions, in the least possible travel time. The ability and effectiveness for the proposed algorithm will be demonstrated by simulation and expeiment.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.900-903
• /
• 1996

The objective of this paper is to make the weighted graph map for path planning using the ultrasonic sensor measurements that are acquired when an A.M.R (autonomous mobile robot) explores the unknown circumstance. First, The A.M.R navigates on unknown space with wall-following and gathers the sensor data from the environments. After this, we constructs the occupancy grid map by interpreting the gathered sensor data to occupancy probability. For the path planning of roadmap method, the weighted graph map is extracted from the occupancy grid map using morphological image processing and thinning algorithm. This methods is implemented on an A.M.R having a ultrasonic sensor.

• Proceedings of the IEEK Conference
• /
• 2009.05a
• /
• pp.378-380
• /
• 2009

For the autonomous movement, the optimal pat]1 planning connecting between current and target positions is essential, and the optimal path of mobile robot means obstacle-free and the shortest length path to a target position. Many actual mobile robots should move without any information of surrounded obstacles. This paper suggests a new method of obstacle avoidment which is suitable in unknown environments. This method of obstacle avoidance is designed with a distributed fuzzy control system, and imitates a Potential Field method. A simulation confirms the performance and correctness of the obstacle avoidance.

• ETRI Journal
• /
• v.43 no.4
• /
• pp.580-593
• /
• 2021

When operating in confined spaces or near obstacles, collision-free path planning is an essential requirement for autonomous exploration in unknown environments. This study presents an autonomous exploration technique using a carefully designed collision-free local planner. Using LiDAR range measurements, a local end-point selection method is designed, and the path is generated from the current position to the selected end-point. The generated path showed the consistent collision-free path in real-time by adopting the Euclidean signed distance field-based grid-search method. The results consistently demonstrated the safety and reliability of the proposed path-planning method. Real-world experiments are conducted in three different mines, demonstrating successful autonomous exploration flights in environment with various structural conditions. The results showed the high capability of the proposed flight autonomy framework for lightweight aerial robot systems. In addition, our drone performed an autonomous mission in the tunnel circuit competition (Phase 1) of the DARPA Subterranean Challenge.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.16-22
• /
• 2024

Robotic grasping in unstructured environments poses a significant challenge, demanding precise estimation of gripping positions for diverse and unknown objects. Generative Grasping Convolution Neural Network (GG-CNN) can estimate the position and direction that can be gripped by a robot gripper for an unknown object based on a three-dimensional depth map. Since GG-CNN uses only a depth map as an input, the precision of the depth map is the most critical factor affecting the result. To address the challenge of depth map precision, we integrate the Segment Anything Model renowned for its robust zero-shot performance across various segmentation tasks. We adjust the components corresponding to the segmented areas in the depth map aligned through external calibration. The proposed method was validated on the Cornell dataset and SurgicalKit dataset. Quantitative analysis compared to existing methods showed a 49.8% improvement with the dataset including surgical instruments. The results highlight the practical importance of our approach, especially in scenarios involving thin and metallic objects.